Instructions to use huggingtweets/danielleboccell with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huggingtweets/danielleboccell with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="huggingtweets/danielleboccell")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/danielleboccell")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/danielleboccell", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/danielleboccell with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huggingtweets/danielleboccell"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huggingtweets/danielleboccell",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huggingtweets/danielleboccell

SGLang

How to use huggingtweets/danielleboccell with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "huggingtweets/danielleboccell" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huggingtweets/danielleboccell",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "huggingtweets/danielleboccell" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huggingtweets/danielleboccell",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huggingtweets/danielleboccell with Docker Model Runner:
```
docker model run hf.co/huggingtweets/danielleboccell
```

boris commited on Apr 1, 2021

Commit

aa82301

1 Parent(s): 4d8959a

New model from https://wandb.ai/wandb/huggingtweets/runs/1eos8bct

Browse files

Files changed (3) hide show

README.md +6 -6
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/danielleboccell/1617303837879/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -32,20 +32,20 @@ The model was trained on [@danielleboccell's tweets](https://twitter.com/daniell
 | Data | Quantity |
 | --- | --- |
-| Tweets downloaded | 2080 |
 | Retweets | 323 |
 | Short tweets | 135 |
-| Tweets kept | 1622 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3pckj2y2/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @danielleboccell's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1cmdsisc) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1cmdsisc/artifacts) is logged and versioned.
 ## How to use

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 | Data | Quantity |
 | --- | --- |
+| Tweets downloaded | 2081 |
 | Retweets | 323 |
 | Short tweets | 135 |
+| Tweets kept | 1623 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3af0f02e/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @danielleboccell's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1eos8bct) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1eos8bct/artifacts) is logged and versioned.
 ## How to use

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d535dbaf9455fbbade9a1ee204d32df202fdc398db170c489ba896af616264e4
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a7c02c33fffca0982c04eca6946ca75a22e325afa2b0260d56066ab9976d64f
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b94b13a11e6ac66916c22748d73cbdada662c80e53d635f4abefb34548d4b63
 size 2287

 version https://git-lfs.github.com/spec/v1
+oid sha256:357d9dd8253d4543615de4b363daf0a1088fbf1562dcd6e8adc9e3d3be8880ab
 size 2287